A Study on Modeling Roman Numeral Analysis Progressions Using the Encoder-Decoder Transformer

This paper evaluates the efficacy and usage of a proposed model built on the encoder-decoder Transformer for the purposes of modeling harmonic progressions rooted in the Western tonality schema using Roman numeral analysis (RNA). A combination of the WhenInRome and Yale-Classical Archives Corpus Lig...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:IEEE International Conference on Electro Information Technology S. 518 - 523
Hauptverfasser: Tucker, Aaron, Omwenga, Maxwell M.
Format: Tagungsbericht
Sprache:Englisch
Veröffentlicht: IEEE 29.05.2025
Schlagworte:
ISSN:2154-0373
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Abstract This paper evaluates the efficacy and usage of a proposed model built on the encoder-decoder Transformer for the purposes of modeling harmonic progressions rooted in the Western tonality schema using Roman numeral analysis (RNA). A combination of the WhenInRome and Yale-Classical Archives Corpus Light corpora produced 8,934 compositions dated around the Common Practice Period, which were then preprocessed to produce a tokenization of each RNA symbol as well as a pitch-class vector corresponding to the unique constituent chord tones of each symbol, transposed to pitch-class 0. Each symbol followed a tokenization schema expressing each symbol in terms of its degree (position in key), tonality (major/minor), form (augmented/diminished), figured bass/inversions, added chord tones, and secondary dominance. The chord tokens and pitch-class vectors are then embedded, summed, and applied to the positional layer to provide the Transformer model with additional harmonic context. We find that while the encoder-decoder model shows promise in its ability to predict next tokens when given simple progressions, it remains limited in its ability to complete more complex progressions by both data sparsity and the structural complexity of RNA. This result is indicative of a) the continuing problem of a lack of systematic and rigorous training data in the field of computational musicology (CM), b) the complexity of RNA as a harmonic language and its continued lack of usage in the midst of more modern forms of communicating harmonic information, and c) the general inefficiency of the practice of generalizing models to specific tasks without large amounts of specialization, such as pretraining or heavy modifications to model architecture. We discuss these problems and suggest solutions to broadening the amount of data available in the CM domain as well as improving the quality of both the model and the (data.
AbstractList This paper evaluates the efficacy and usage of a proposed model built on the encoder-decoder Transformer for the purposes of modeling harmonic progressions rooted in the Western tonality schema using Roman numeral analysis (RNA). A combination of the WhenInRome and Yale-Classical Archives Corpus Light corpora produced 8,934 compositions dated around the Common Practice Period, which were then preprocessed to produce a tokenization of each RNA symbol as well as a pitch-class vector corresponding to the unique constituent chord tones of each symbol, transposed to pitch-class 0. Each symbol followed a tokenization schema expressing each symbol in terms of its degree (position in key), tonality (major/minor), form (augmented/diminished), figured bass/inversions, added chord tones, and secondary dominance. The chord tokens and pitch-class vectors are then embedded, summed, and applied to the positional layer to provide the Transformer model with additional harmonic context. We find that while the encoder-decoder model shows promise in its ability to predict next tokens when given simple progressions, it remains limited in its ability to complete more complex progressions by both data sparsity and the structural complexity of RNA. This result is indicative of a) the continuing problem of a lack of systematic and rigorous training data in the field of computational musicology (CM), b) the complexity of RNA as a harmonic language and its continued lack of usage in the midst of more modern forms of communicating harmonic information, and c) the general inefficiency of the practice of generalizing models to specific tasks without large amounts of specialization, such as pretraining or heavy modifications to model architecture. We discuss these problems and suggest solutions to broadening the amount of data available in the CM domain as well as improving the quality of both the model and the (data.
Author Tucker, Aaron
Omwenga, Maxwell M.
Author_xml – sequence: 1
  givenname: Aaron
  surname: Tucker
  fullname: Tucker, Aaron
  email: at273@evansville.edu
  organization: School of Engineering and Computer Science, University of Evansville,IN,USA
– sequence: 2
  givenname: Maxwell M.
  surname: Omwenga
  fullname: Omwenga, Maxwell M.
  email: mo138@evansville.edu
  organization: School of Engineering and Computer Science, University of Evansville,IN,USA
BookMark eNo1kN1KAzEUhKMoWGvfQCQvsPUkZzfZXJbaaqH-oOullGR7tq5sE0nai76969_VwDDfMMw5O_HBE2NXAsZCgLmmRaVyNGIsQRa9JQAV6iM2MtqUiKJAiVges4EURZ4Bajxjo5Q-AKDHlZHlgL1N-Mtuvz7w4Pl9WFPX-g1_Dlvr-cN-S9F2fOJtd0ht4k8xbCKl1Aaf-Gv6Tu7eic983YMxu6Ef5VW0PjUh9vQFO21sl2j0p0NWzWfV9C5bPt4uppNl1hrcZc5Jp-pC5s71m0SdF7rURMpZMA2UuQAtHDRCOaG0q9eGag2yj2qpUJQWh-zyt7YlotVnbLc2Hlb_h-AXBE5WvA
ContentType Conference Proceeding
DBID 6IE
6IL
CBEJK
RIE
RIL
DOI 10.1109/eIT64391.2025.11103637
DatabaseName IEEE Electronic Library (IEL) Conference Proceedings
IEEE Xplore POP ALL
IEEE Xplore All Conference Proceedings
IEEE Electronic Library (IEL)
IEEE Proceedings Order Plans (POP All) 1998-Present
DatabaseTitleList
Database_xml – sequence: 1
  dbid: RIE
  name: IEEE Electronic Library (IEL)
  url: https://ieeexplore.ieee.org/
  sourceTypes: Publisher
DeliveryMethod fulltext_linktorsrc
EISBN 9798331532338
EISSN 2154-0373
EndPage 523
ExternalDocumentID 11103637
Genre orig-research
GroupedDBID 6IE
6IF
6IH
6IK
6IL
6IN
AAJGR
AAWTH
ABLEC
ACGFS
ADZIZ
ALMA_UNASSIGNED_HOLDINGS
BEFXN
BFFAM
BGNUA
BKEBE
BPEOZ
CBEJK
CHZPO
IEGSK
IPLJI
OCL
RIE
RIL
RNS
ID FETCH-LOGICAL-i93t-bb2b6c524bb9281c45787ee6ba09f0841071b0f16b167bcd9ec702928726318a3
IEDL.DBID RIE
IngestDate Wed Aug 20 06:20:55 EDT 2025
IsPeerReviewed false
IsScholarly false
Language English
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-i93t-bb2b6c524bb9281c45787ee6ba09f0841071b0f16b167bcd9ec702928726318a3
PageCount 6
ParticipantIDs ieee_primary_11103637
PublicationCentury 2000
PublicationDate 2025-May-29
PublicationDateYYYYMMDD 2025-05-29
PublicationDate_xml – month: 05
  year: 2025
  text: 2025-May-29
  day: 29
PublicationDecade 2020
PublicationTitle IEEE International Conference on Electro Information Technology
PublicationTitleAbbrev EIT
PublicationYear 2025
Publisher IEEE
Publisher_xml – name: IEEE
SSID ssj0001096928
Score 1.9099317
Snippet This paper evaluates the efficacy and usage of a proposed model built on the encoder-decoder Transformer for the purposes of modeling harmonic progressions...
SourceID ieee
SourceType Publisher
StartPage 518
SubjectTerms Analytical models
Complexity theory
Computational modeling
Computational musicology
Data models
Harmonic analysis
harmonic generation
NLP
RNA
Symbols
Tokenization
Transformer
Transformers
Vectors
Title A Study on Modeling Roman Numeral Analysis Progressions Using the Encoder-Decoder Transformer
URI https://ieeexplore.ieee.org/document/11103637
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlZ07T8MwEIAtWjEwAaKItzywuk2c2I5HBK1gqSqUoQuqYueCOuCgtKnEv8fnNlQMDEx5KFakO53ufHefj5D7quJFokvLjPc_LI1NwnQlJBPKau8dRCmsDcMm1HSazed6toPVAwsDAKH5DIZ4G2r5ZW1bTJWNvF1i3VH1SE8puYW19gkVH4xrnu0oYP80gpc8gKV-F8jFsFv8a4xK8CKT43_-_4QM9jwenf14mlNyAO6MvD1QbAL8orWjONEMuXL6Wn8Ujk7bkGqi3YkjuPh92_DqVjR0CVAf-NGxQ6K9YU8QrjTvolhoBiSfjPPHZ7YblsCWOlkzY7iRVvDUGC-E2KZoiQDSFJGuoiz1u7zYRFUsTSyVsaUGqyLuP1VcerMuknPSd7WDC0KFV1uRJlYUyJ2a1ABW40ofB6gkiyp-SQYomsXn9jiMRSeVqz_eX5MjVACW3Lm-If1108ItObSb9XLV3AUlfgPW3pzY
linkProvider IEEE
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1NT8MwDI1gIMEJEEN8kwPXbG3atM0RwaZNjGpCPeyCpiZ1EQdS1G1I_HvirGXiwIFT2yiRKluWHdvPj5DbsuR5IAvNlPU_LPRVwGQpIiZiLa13EIXQ2pFNxGmazGZy2oDVHRYGAFzzGfTw1dXyi0qvMFXWt3aJdcd4m-wgdVYD19qkVGw4LnnS4IDtVx_GmYOW2nsgF732-C8iFedHhgf__IND0t0g8uj0x9cckS0wx-TljmIb4BetDEVOM0SW0-fqPTc0XblkE21njuDh13XLq1lQ1ydAbehHBwYx7TV7APekWRvHQt0l2XCQ3Y9YQ5fA3mSwZEpxFWnBQ6WsEHwdoi0CRCr3ZOklob3n-cor_Uj5Uax0IUHHHrdbYx5Zw86DE9IxlYFTQoVVXB4GWuSIPFWhAqzHFTYSiIPEK_kZ6aJo5h_rgRjzVirnf6zfkL1R9jSZT8bp4wXZR2VgAZ7LS9JZ1iu4Irv6c_m2qK-dQr8BM-egIQ
openUrl ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Abook&rft.genre=proceeding&rft.title=IEEE+International+Conference+on+Electro+Information+Technology&rft.atitle=A+Study+on+Modeling+Roman+Numeral+Analysis+Progressions+Using+the+Encoder-Decoder+Transformer&rft.au=Tucker%2C+Aaron&rft.au=Omwenga%2C+Maxwell+M.&rft.date=2025-05-29&rft.pub=IEEE&rft.eissn=2154-0373&rft.spage=518&rft.epage=523&rft_id=info:doi/10.1109%2FeIT64391.2025.11103637&rft.externalDocID=11103637